检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Dorri, Ali Kanhere, Salil S. Jurdak, Raja Gauravaram, Praveen School of computer science and engineering UNSW Sydney Australia DATA61 CSIRO Brisbane Australia Tata Consultancy Services Brisbane Australia

BlockChain \(BC\) has attracted tremendous attention due to its immutable nature and the associated security and privacy benefits. BC has the potential to overcome security and privacy challenges of Internet of Things \(IoT\). However, BC is computationally expensive, has limited scalability and incurs significant bandwidth overheads and delays which are not suited to the IoT context. We propose a tiered Lightweight Scalable BC \(LSB\) that is optimized for IoT requirements. We explore LSB in a smart home setting as a representative example for broader IoT applications. Low resource devices in a smart home benefit from a centralized manager that establishes shared keys for communication and processes all incoming and outgoing requests. LSB achieves decentralization by forming an overlay network where high resource devices jointly manage a public BC that ensures end-to-end privacy and security. The overlay is organized as distinct clusters to reduce overheads and the cluster heads are responsible for managing the public BC. LSB incorporates several optimizations which include algorithms for lightweight consensus, distributed trust and throughput management. Qualitative arguments demonstrate that LSB is resilient to several security attacks. Extensive simulations show that LSB decreases packet overhead and delay and increases BC scalability compared to relevant baselines. Copyright © 2017, The Authors. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Gloss-Free Sign Language Translation using Sign2gpt-Next Technique

Gloss-Free Sign Language Translation using Sign2gpt-Next Tec...

引用

Computing and Intelligent Reality Technologies (ICCIRT), International Conference on

作者： A. Babisha G. Umarani Srikanth D.R. Angel Kiruba R Sundar Department of Artificial Intelligence and Data Science Panimalar Engineering College Chennai India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Computer Science and Engineering DMI College of Engineering Chennai India Department of Computer Science and Engineering School of Computing Sathyabama Institute of Science and Technology Chennai India

ISBN: (数字)9798331510299

ISBN: (纸本)9798331510305

This work proposes a new approach to convert the data from sign language to spoken language without exposing the data to a gloss layer. Whenever gloss annotations are used which frequently are incomplete and act as an intermediate representation, it is usually found to be a bottleneck in translating sign language videos. In order to avoid this, the authors use a combination of modern machine learning algorithms to arrive at the conclusion. They use Dino-V2 Vision Transformer to implement the function of extracting the spatial features of the input sign language video frames. This model is particularly suitable for learning and visual patterns in general and particularly for capturing fine details of these patterns. Further, a spatio-temporal transformer layer is added to automate the temporal processing of the Sign-Language which helps in the arrangement of the body gestures and limb movements needed at a specific temporal frame. It is then translated into the desired spoken language using a multilingual Generative Pre-trained Transformer (GPT) model. The approach can be said to be a big leap forward in sign language transliteration especially for such situations where few Gloss annotations are available, and making way for better and improved tools for the Deaf and the hard-of-hearing.

关键词： Sign language Visualization Translation Annotations Generative Pre-trainer transformer Transformers Feature extraction Multilingual Optimization Videos

来源：评论

学校读者我要写书评

暂无评论

Towards Cascading Problem for Dynamic Rate Allocations in ISP Networks with SDN

Towards Cascading Problem for Dynamic Rate Allocations in IS...

引用

International Conference on Mobile Ad-hoc and Sensor Networks, MSN

作者： Chao Song Jiqing Gu Lei Shi Yongqiang Qi Ming Liu School of Computer Science and Engineering University of Electronic Science and Technology of China Big Data Research Center University of Electronic Science and Technology of China

ISBN: (数字)9781728152127

ISBN: (纸本)9781728152134

To improve the experience of various network applications, dynamic rate allocation is an essential issue in recent ISP networks. The emergence of software-defined networking (SDN) and the OpenFlow specification makes dynamic rate allocation in ISP networks efficient. The allocation could locally run on a home network gateway (edge switch) under SDN, but such local range of rate allocation reduces the overall fairness and performance in the whole network. However, under a global range, the request of rate allocation from a small number of hosts will cause all switches on the entire network to participate. This is termed as cascading problem, which causes a high cost for re-allocating the rates with the global range of switches. In this paper, we investigate the cascading problem for dynamic rate allocation with SDN, and discuss the tradeoff between the performance and cost for the range of rate allocation. We propose a Rate Allocation algorithm with Limited Range (RALR) in SDN, and discuss it for dynamic rate allocation by the theory of Lyapunov drift. Our intensive simulations verify the performance of the proposed strategy of rate allocation in SDN.

关键词： Resource management Switches Dynamic scheduling Meters Bandwidth Internet

来源：评论

学校读者我要写书评

暂无评论

A lightweight and efficient raw data collection scheme for IoT systems

引用

Journal of Information and Intelligence 2024年第3期2卷 209-223页

作者： Yixuan Huang Yining Liu Jingcheng Song Weizhi Meng School of Computer and Information Security Guilin University of Electronic TechnologyGuilin 541004China School of Data Science and Artificial Intelligence Wenzhou University of TechnologyWenzhou 325027China School of Computer Science&Engineering LinYi UniversityLinyi 276000China Department of Aplied Mathematics and Computer Science Technical University of DenmarkKongens Lyngby 2800Denmark

With the prevalence of Internet of Things(loT)devices,data collection has the potential to improve people's lives and create a significant ***,it also exposes sensitive information,which leads to privacy *** approach called N-source anonymity has been used for privacy preservation in raw data collection,but most of the existing schemes do not have a balanced efficiency and *** this work,a lightweight and efficient raw data collection scheme is *** proposed scheme can not only collect data from the original users but also protect their ***,the proposed scheme can resist user poisoning attacks,and the use of the reward method can motivate users to actively provide *** and simulation indicate that the proposed scheme is safe against poison ***,the proposed scheme has better performance in terms of computation and communication overhead compared to existing *** efficiency and appropriate incentive mechanisms indicate that the scheme is practical for IoT systems.

关键词： data privacy Raw data collection loT systems Unlinkability

来源：评论

学校读者我要写书评

暂无评论

Chatbot: An automated conversation system for the educational domain

Chatbot: An automated conversation system for the educationa...

引用

International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)

作者： Anupam Mondal Monalisa Dey Dipankar Das Sachit Nagpal Kevin Garda Computer Science and Engineering Jadavpur University Kolkata India Big Data and Analytics S P Jain School of Global Management Mumbai India

ISBN: (纸本)9781728101651;9781728101644

Speech and textual information play a crucial role in communicating between humans. An article in “The New York Times” published that now-a-days the adults are spending more than 8 hours a day on screens of computers or mobiles. So the major communication between humans is conducted through web applications such as WhatsApp, Facebook, and Twitter etc as a form of speech and textual conversation. In the present paper, we have focused on designing a textual communication application namely chatbot in the educational domain. The proposed chatbot assists in answering questions provided by the users. To develop the system, we have employed an ensemble learning method as random forest in the presence of extracted features from our prepared dataset. Besides, the validation system offers an average F-measure 0.870 score on various K-values under random forest for the proposed chatbot. Finally, we have deployed the proposed system in a from of telegram bot.

关键词： Chatbot Feature extraction Random forests Vegetation Decision trees Training data Organizations

来源：评论

学校读者我要写书评

暂无评论

Hate Speech Detection using ML algorithms

Hate Speech Detection using ML algorithms

引用

Artificial Intelligence and Machine Vision (AIMV), International Conference on

作者： Aditya Razdan Shridevi. S School of Computer Science and Engineering Vellore Institute of Technology Chennai India Centre for Advanced Data Science Vellore Institute of Technology Chennai India

ISBN: (纸本)9781665442121

Social media is a growing platform where different users share their ideas and sentiments towards different topics because users spend a lot of time expressing their thoughts and views. There are various researches going on in detecting the sentiments of the user’s comments but the main sentiment factor remain undiagnosed. In this paper, the aim is to detect hate speeches. The dataset was preprocessed and cleaned and cleaned text was explored to get a better understanding. Salient features were extracted from the data to train our model and to identify the hate sentiments of tweets. The vector model is created using genism to learn the relationship between words and based on that sentence are labeled. Stop words and port stemmer are used to filter unwanted data to build the vocabulary using CountVectorizer before it is used for model building. Using various machine algorithms, comparative study is done to check the performance of algorithms and promising results are attained.

关键词： Analytical models Vocabulary Social networking (online) Hate speech Prediction algorithms Feature extraction data models

来源：评论

学校读者我要写书评

暂无评论

Research on Revit-Based Turning Algorithm of Climbing Frame Type Mold for High-Rise Building Construction

Research on Revit-Based Turning Algorithm of Climbing Frame ...

引用

Chinese Automation Congress (CAC)

作者： Hui Zhong JingKai Huang Liaoning Province Big Data Management and Analysisline Laboratory of Urban Construction School of Computer Science and Engineering Shenyang Jianzhu University Shenyang China

To assist the Construction of a climbing frame for high-rise building construction and enrich the family of climbing frame parts, this paper proposes an algorithm for the molding of climbing frame parts, which automatically molds the Revit 3D model and forms the family file according to the CAD 2D drawings of climbing frame parts. The original information, such as text and geometric elements in the drawing of the part, is extracted in Revit. The algorithm is designed to calculate the data such as bottom profile, height, and hole position, and the 3D model of the part is built, and the family of the part is formed by stretching the bottom profile and cutting the hole. For the same type of parts, the differences between the parts are parameterized, and the structure of the parts is determined according to the parameters. The model is built, and the family of parts is formed. It improves the design efficiency of the climbing frame for high-rise building construction, lays the foundation for the subsequent overall design of the climbing frame, and provides specific value in promoting the application of BIM technology in the architectural design industry.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel XGBoost Tuned Machine Learning Model for Software Bug Prediction

Novel XGBoost Tuned Machine Learning Model for Software Bug ...

引用

Intelligent engineering and Management (ICIEM), International Conference on

作者： Aashish Gupta Shilpa Sharma Shubham Goyal Mamoon Rashid School of Computer Science and Engineering Lovely Professional University Jalandhar India Data Scientist Knoldus Inc. Noida Uttar Pradesh India

ISBN: (数字)9781728140971

ISBN: (纸本)9781728140988

As internet users grow, the quantity of data available on the web increases with it. Virtually everything that needs human effort or human presence can be replaced by the Software. While developing an application it follows the Software Development Lifecycle (SDLC). Within the early stages of development, it's a compulsory task to take care of system or bugs to avoid wasting time and effort during initial development phase to forestall any runtime crisis. In this paper, we used the machine learning models - Logistic regression, Decision Tree, Random Forest, Adaboost and XGBoost as state-of-art models for four datasets of NASA-KC2, PC3, JM1, CM1. Later on, new model was proposed based on tuning the existing XGBoost model by changing its parameter namely N_estimator, learning rate, max depth, and subsample. The results achieved were compared with state-of-art models and our model outperformed them for all datasets. The authors believe that this research will contribute in correctly detecting the bugs with machine learning approach.

关键词： Tuning computer bugs Software Machine learning Forestry Logistics Predictive models

来源：评论

学校读者我要写书评

暂无评论

Overcoming data Inequality across Domains with Semi-Supervised Domain Generalization

arXiv

引用

arXiv 2024年

作者： Park, Jinha Cho, Wonguk Kim, Taesup Department of Electrical and Computer Engineering Seoul National University Korea Republic of Graduate School of Data Science Seoul National University Korea Republic of

While there have been considerable advancements in machine learning driven by extensive datasets, a significant disparity still persists in the availability of data across various sources and populations. This inequality across domains poses challenges in modeling for those with limited data, which can lead to profound practical and ethical concerns. In this paper, we address a representative case of data inequality problem across domains termed Semi-Supervised Domain Generalization (SSDG), in which only one domain is labeled while the rest are unlabeled. We propose a novel algorithm, ProUD, which can effectively learn domain-invariant features via domain-aware prototypes along with progressive generalization via uncertainty-adaptive mixing of labeled and unlabeled domains. Our experiments on three different benchmark datasets demonstrate the effectiveness of ProUD, outperforming all baseline models including single domain generalization and semi-supervised learning. Source code will be released upon acceptance of the paper. Copyright © 2024, The Authors. All rights reserved.

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

From categorical to numerical: Multiple transitive distance learning and embedding

From categorical to numerical: Multiple transitive distance ...

引用

SIAM International Conference on data Mining 2015, SDM 2015

作者： Zhang, Kai Wang, Qiaojun Chen, Zhengzhang Marsic, Ivan Kumar, Vipin Jiang, Guofei Zhang, Jie School of Computer Science Southwest Petroleum University Chengdu Sichuan Province610500 China Institute of Data Science and Technology Alibaba Group SeattleWA98101 United States Department of Electrical and Computer Engineering Rutger-s the State University of New Jersey NJ08854 United States NEC Laboratories America Inc. PrincetonNJ08540 United States Department of Electrical Engineering and Computer Science Northwestern University EvanstonIL60208 United States Department of Computer Science and Engineering University of Minnesota MinneapolisMN55455 United States Center for Computational Systems Biology Fudan University Shanghai200433 China

ISBN: (纸本)9781510811522

Categorical data are ubiquitous in real-world databases. However, due to the lack of an intrinsic proximity measure, many powerful algorithms for numerical data analysis may not work well on their categorical counterparts, making it a bottleneck in practical applications. In this paper, we propose a novel method to transform categorical data to numerical representations, so that abundant numerical learning methods can be exploited in categorical data mining. Our key idea is to learn a pairwise dissimilarity among categorical symbol-s, henceforth a continuous embedding, which can then be used for subsequent numerical treatment. There are two important criteria for learning the dissimilarities. First, it should capture the important "transitivity" which has shown to be particularly useful in measuring the proximity relation in categorical data. Second, the pairwise sample geometry arising from the learned symbol distances should be maximally consistent with prior knowledge (e.g., class labels) to obtain a good generalization performance. We achieve them through multiple transitive distance learning and embedding. Encouraging results are observed on a number of benchmark classification tasks against state-of-the-art. Copyright © SIAM.

关键词： Distance education

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：